Safeguarding Multimodal Knowledge Copyright in the RAG-As-A-Service Environment

As Retrieval-Augmented Generation RAG evolves into service-oriented platforms Rag-as-a-Service with shared knowledge bases, protecting the copyright of contributed data becomes essential. Existing watermarking methods in RAG focus solely on textual knowledge, leaving image knowledge unprotected. ...

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing

Diffusion models DMs have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright infringement. Concept erasing finetunes weights to unlearn...

Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond

The quantity and quality of vulnerability datasets are essential for developing deep learning solutions to vulnerability-related tasks. Due to the limited availability of vulnerabilities, a common approach to building such datasets is analyzing security patches in source code. However, existing...

Adversarial Text Generation with Dynamic Contextual Perturbation

Adversarial attacks on Natural Language Processing NLP models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically focus on word-level or local text segment alterations,...

Towards Generalized Source Tracing for Codec-Based Deepfake Speech

Recent attempts at source tracing for codec-based deepfake speech CodecFake, generated by neural audio codec-based speech generation CoSG models, have exhibited suboptimal performance. However, how to train source tracing models using simulated CoSG data while maintaining strong performance on re...

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Vision Language Models VLMs have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of...

QualitEye: Public and Privacy-Preserving Gaze Data Quality Verification

Gaze-based applications are increasingly advancing with the availability of large datasets but ensuring data quality presents a substantial challenge when collecting data at scale. It further requires different parties to collaborate, therefore, privacy concerns arise. We propose QualitEye--the...

Obfuscation-Resilient Binary Code Similarity Analysis Using Dominance Enhanced Semantic Graph

Binary code similarity analysis BCSA serves as a core technique for binary analysis tasks such as vulnerability detection. While current graph-based BCSA approaches capture substantial semantics and show strong performance, their performance suffers under code obfuscation due to the unstable...

What Really Is a Member? Discrediting Membership Inference Via Poisoning

Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often fail under the strict definition of membership based on exact matching, and have suggested relaxing this definition t...

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models

The protection of cyber Intellectual Property IP such as web content is an increasingly critical concern. The rise of large language models LLMs with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators. As users...

Explainer-Guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models

Binary code similarity detection BCSD serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming at misleading the models to generate erroneous predictions...

Semantic-Preserving Adversarial Attacks on LLMs: an Adaptive Greedy Binary Search Approach

Large Language Models LLMs increasingly rely on automatic prompt engineering in graphical user interfaces GUIs to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended misinterpretations, where automated optimizations distort...

LLM-Driven APT Detection for 6G Wireless Networks: a Systematic Review and Taxonomy

Sixth Generation 6G wireless networks, which are expected to be deployed in the 2030s, have already created great excitement in academia and the private sector with their extremely high communication speed and low latency rates. However, despite the ultra-low latency, high throughput, and...

CVE-2024-51898

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in sachin8600 Semantic Shortcode semantic-shortcode allows Stored XSS.This issue affects Semantic Shortcode: from n/a through = 1.0.1...

CVE-2023-24429

Jenkins Semantic Versioning Plugin 1.14 and earlier does not restrict execution of an controller/agent message to agents, and implements no limitations about the file path that can be parsed, allowing attackers able to control agent processes to have Jenkins parse a crafted file that uses externa...

CVE-2023-22665

There is insufficient checking of user queries in Apache Jena versions 4.7.0 and earlier, when invoking custom scripts. It allows a remote user to execute arbitrary javascript via a SPARQL query...

CVE-2022-48614

Special:Ask in Semantic MediaWiki before 4.0.2 allows Reflected XSS...

Can ChatGPT Perform Image Splicing Detection? A Preliminary Study

Multimodal Large Language Models MLLMs like GPT-4V are capable of reasoning across text and image modalities, showing promise in a variety of complex vision-language tasks. In this preliminary study, we investigate the out-of-the-box capabilities of GPT-4V in the domain of image forensics,...

Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs

Whitepaper called Blind Spot Navigation: Evolutionary Discovery Of Sensitive Semantic Concepts For LVLMs...

Prink: $K_s$-Anonymization for Streaming Data in Apache Flink

In this paper, we present Prink, a novel and practically applicable concept and fully implemented prototype for ks-anonymizing data streams in real-world application architectures. Building upon the pre-existing, yet rudimentary CASTLE scheme, Prink for the first time introduces semantics-aware...